4-5B Parameter LLMs — Page 24

qwen3-4b-agent-v11

dpo-qwen3_4b-cot-merged_v260301-151110

dpo-qwen-cot-merged

dpo-qwen3_4b-cot-merged_v260302-010243

Qwen3-4B-Thinking-2507-Genius-v2

Qwen3-4B-Base-Continued-GRPO-Style-Karcher

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

LLM2025_main_002_full

qwen_finetune_16bit

adv_sft_dpo_final_10_merged

parser_model_ner_3.99

qwen3-4b-instruct-meta-refined1

Qwen3-4B-GRPO-v5-merged

agent-bench-merged12

dpo-qwen3_4b-cot-merged_v260302-112329

tmax-qwen3-4b-sft-20260316-100k-asst-loss

tmax-qwen3-4b-sft-20260316-100k-asst-loss

parser_model_ner_4.05

Affine-5E2HvD7UYbZhusRonAmWoKTLehf3RKWZ9XcUn1K4h879VYq9

Qwen3-4B-Base-ftjob-0511c5edc14e

qwen3-4b-abliterated

Akkadian-Finetune-Qwen3-4B-Merged-16B

olympiad-curated-qwen3-4b-nemotron-5ep

sft_merged_model

student_feedback_v1_Qwen3-4B-Base

Qwen3-4B-Base-ascii-art-v5-lr2e-5-ga16-ctx4096

Devjalx-4b

Qwen3-4B-ESG-IRM-instruct-qa-alpha1.2

Qwen3-4B-Base-ascii-art-v5-no140k-e3-lr5e-5-ga16-ctx4096

mllm-cogrpo-heter-internvl35-2b-x-gemma3-4b-mmr1-groupB-gemma3-4b

amoral-gemma3-4B-v2-qat

Qwen3-4B-v0.3-deepresearch-100-step

qwen3_4blrablation_filtered_0503_lr1e6

Phi3_unlearned

Qwen3-4B-chess-10K-single-move-sft-2025-05-06-red-short-cot-filter-2k-lr-3e-5-checkpoint-110

Extrapolis-4B-SFT

Gemma-3-R1984-4B

gemma-3-4b-it-shqip-v3

Capella-Qwen3-DS-V3.1-4B

WilR-mini

Beck-4B

jade_qwen3_4b